Vinayak Gupta

ML Researcher
Lawrence Livermore National Lab

CV

Research Interests

  • AI for Time Series and Health: Methods and benchmarks for large models (including LLMs) for time series derived from medical records, health devices, and recommender systems.

Education

Ph.D. in Machine Learning

Indian Institute of Technology, Delhi
2017 - 2022

B.Tech in Computer Science

Indian Institute of Information Technology, Jabalpur
2013 - 2017

Skills

  • Proficient: Python: Pytorch.
  • Basics: Tensorflow and MATLAB.

Service

  • PC Member: AAAI, IJCAI, WWW, WSDM, SIGIR, IEEE TPAMI, ACM TOIS, ICML Workshops, etc.


Main Page


Preprints

SPML: A DSL for Defending Language Models Against Prompt Attacks.
Reshabh K Sharma, Vinayak Gupta, and Dan Grossman.
Under Review.
[Code & Dataset]
Efficient and Responsible Adaptation of Large Language Models for Robust and Equitable Top-k Recommendations.
Kirandeep Kaur, Manya Chadha, Vinayak Gupta, and Chirag Shah.
Under Review.
[Code]

All Publications

2025
Differentiable Adversarial Attacks for Marked Temporal Point Processes.
Pritish Chakraborty*, Vinayak Gupta*, Rahul R, Srikanta Bedathur, and Abir De.
AAAI Conference on Artificial Intelligence (AAAI), 2025.
[Code]
Enhancing Biological Insights with Knowledge-Driven Multi-Modal RNA Models.
Mufan Qiu, Sukwon Yun, Ruichen Zhang, Joseph Wakim, Jonathan Allen, Jose Manuel Marti, Vinayak Gupta, Brian Bartoldson, Bhavya Kailkhura, and Tianlong Chen.
US DOE Workshop on Envisioning Frontiers in AI and Computing for Biological Research, 2025.
[Code]
2024
Are Language Models Actually Useful for Time Series Forecasting?
Mingtian Tan, Mike A. Merrill, Vinayak Gupta, Tim Althoff, and Tom Hartvigsen.
Neural Information Processing Systems (NeurIPS), 2024. (Spotlight Paper)
[Code]
Language Models Still Struggle to Zero-shot Reason about Time Series.
Mike A. Merrill, Mingtian Tan, Vinayak Gupta, Tom Hartvigsen, and Tim Althoff.
Findings of Emperical Methods in Natural Langauge Processing (EMNLP), 2024.
[Code]
Defending Language Models Against Image-Based Prompt Attacks via User-Provided Specifications.
Reshabh Sharma, Vinayak Gupta, and Dan Grossman.
Security Architectures for Generative Artificial Intelligence Workshop (SAGAI@S&P), 2024.
[Code]
2023
Retrieving Continuous Time Event Sequences using Neural Temporal Point Processes with Learnable Hashing.
Vinayak Gupta, Srikanta Bedathur, and Abir De.
ACM Transactions on Intelligent Systems and Technology (TIST), 2023.
[Code]
Tapestry of Time and Actions: Modeling Human Activity Sequences using Temporal Point Process Flows.
Vinayak Gupta and Srikanta Bedathur.
ACM Transactions on Intelligent Systems and Technology (TIST), 2023.
[Code]
Modeling Spatial Trajectories using Coarse-Grained Smartphone Logs.
Vinayak Gupta and Srikanta Bedathur.
IEEE Transactions on Big Data (TBD), 2023.
[Code]
Teaching Old DB Neural Tricks: Learning Embeddings on Multi-tabular Databases.
Garima Gaur, Rajat Singh, Siddhant Arora, Vinayak Gupta, and Srikanta Bedathur
Conference on Data Science & Management of Data (CODS-COMAD), 2023.
[Code]
2022
Learning Temporal Point Processes for Efficient Retrieval of Continuous Time Event Sequences.
Vinayak Gupta, Srikanta Bedathur, and Abir De.
AAAI Conference on Artificial Intelligence (AAAI), 2022.
[Code]
ProActive: Self-Attentive Temporal Point Process Flows for Activity Sequences.
Vinayak Gupta and Srikanta Bedathur.
ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2022.
[Code]
Modeling Continuous Time Sequences with Intermittent Observations using Marked Temporal Point Processes.
Vinayak Gupta, Srikanta Bedathur, Sourangshu Bhattacharya, and Abir De.
ACM Transactions on Intelligent Systems and Technology (TIST), 2022.
[Code]
Doing More with Less: Overcoming Data Scarcity for POI Recommendation via Cross-Region Transfer.
Vinayak Gupta and Srikanta Bedathur.
ACM Transactions on Intelligent Systems and Technology (TIST), 2022.
[Code]
A Neural Approach for Modeling Continuous Time Sequences with Intermittent Observations.
Vinayak Gupta, Srikanta Bedathur, Sourangshu Bhattacharya, and Abir De.
ACM India Academic Research and Careers for Students Symposium (ARCS), 2022.
[Code]   Oral Paper
Modeling Human Actions in Time-Stamped Activity Sequences.
Vinayak Gupta and Srikanta Bedathur.
Applied Machine Learning for Time Series Forecasting Workshop (AMLTS@CIKM), 2022.
[Code]
Advances in NLP Research for Automated Business Intelligence.
Vinayak Gupta, Rajmohan C, Ritwik Chaudhuri, Ankush Gupta, Balaji Ganesan, Arvind Agarwal, and Sameep Mehta.
Tutorial at International Conference on Natural Language Processing (ICON), 2022.
[Slides]
2021
Learning Temporal Point Processes with Intermittent Observations.
Vinayak Gupta, Srikanta Bedathur, Sourangshu Bhattacharya, and Abir De.
International Conference on Artificial Intelligence and Statistics (AISTATS), 2021.
[Code]
Region Invariant Normalizing Flows for Mobility Transfer.
Vinayak Gupta and Srikanta Bedathur.
ACM International Conference on Information and Knowledge Management (CIKM), 2021.
[Code]
Learning Neural Models for Continuous-Time Sequences.
Vinayak Gupta
International Conference on AI-ML-Systems, Doctoral Symposium (AI-ML-Systems), 2021.
Outstanding Doctoral Paper Award
2020 and before
Modeling Implicit Communities from Geo-tagged Event Traces using Spatio-Temporal Point Processes.
Ankita Likhyani*, Vinayak Gupta*, P.K. Srijith, P. Deepak, and Srikanta Bedathur.
International Conference on Web Information Systems Engineering (WISE), 2020.
[Code]
LBRR: Load Balanced Ring Routing Protocol for Heterogeneous Sensor Networks with Sink Mobility.
Sonam Maurya*, Vinayak Gupta*, and V.K. Jain.
IEEE Wireless Communications and Networking Conference (WCNC), 2017.
[Code]